DetCLIPv3: Towards Versatile Generative Open-vocabulary Object Detection

Existing open-vocabulary object detectors typically require a predefined set of categories from users, significantly confining their application scenarios. In this paper, we introduce DetCLIPv3, a high-performing detector that excels not only at both open-vocabulary object detection, but also generating hierarchical labels for detected objects. DetCLIPv3 is characterized by three core designs: 1. Versatile model architecture: we derive a robust open-set detection framework which is further empowered with generation ability via the integration of a caption head. 2. High information density data: we develop an auto-annotation pipeline leveraging visual large language model to refine captions for large-scale image-text pairs, providing rich, multi-granular object labels to enhance the training. 3. Efficient training strategy: we employ a pre-training stage with low-resolution inputs that enables the object captioner to efficiently learn a broad spectrum of visual concepts from extensive image-text paired data. This is followed by a fine-tuning stage that leverages a small number of high-resolution samples to further enhance detection performance. With these effective designs, DetCLIPv3 demonstrates superior open-vocabulary detection performance, \eg, our Swin-T backbone model achieves a notable 47.0 zero-shot fixed AP on the LVIS minival benchmark, outperforming GLIPv2, GroundingDINO, and DetCLIPv2 by 18.0/19.6/6.6 AP, respectively. DetCLIPv3 also achieves a state-of-the-art 19.7 AP in dense captioning task on VG dataset, showcasing its strong generative capability.

MLP Can Be A Good Transformer Learner

Self-attention mechanism is the key of the Transformer but often criticized for its computation demands. Previous token pruning works motivate their methods from the view of computation redundancy but still need to load the full network and require same memory costs. This paper introduces a novel strategy that simplifies vision transformers and reduces computational load through the selective removal of non-essential attention layers, guided by entropy considerations. We identify that regarding the attention layer in bottom blocks, their subsequent MLP layers, i.e. two feed-forward layers, can elicit the same entropy quantity. Meanwhile, the accompanied MLPs are under-exploited since they exhibit smaller feature entropy compared to those MLPs in the top blocks. Therefore, we propose to integrate the uninformative attention layers into their subsequent counterparts by degenerating them into identical mapping, yielding only MLP in certain transformer blocks. Experimental results on ImageNet-1k show that the proposed method can remove 40% attention layer of DeiT-B, improving throughput and memory bound without performance compromise. Code is available at https://github.com/sihaoevery/lambda_vit.

LayerDiff: Exploring Text-guided Multi-layered Composable Image Synthesis via Layer-Collaborative Diffusion Model

Despite the success of generating high-quality images given any text prompts by diffusion-based generative models, prior works directly generate the entire images, but cannot provide object-wise manipulation capability. To support wider real applications like professional graphic design and digital artistry, images are frequently created and manipulated in multiple layers to offer greater flexibility and control. Therefore in this paper, we propose a layer-collaborative diffusion model, named LayerDiff, specifically designed for text-guided, multi-layered, composable image synthesis. The composable image consists of a background layer, a set of foreground layers, and associated mask layers for each foreground element. To enable this, LayerDiff introduces a layer-based generation paradigm incorporating multiple layer-collaborative attention modules to capture inter-layer patterns. Specifically, an inter-layer attention module is designed to encourage information exchange and learning between layers, while a text-guided intra-layer attention module incorporates layer-specific prompts to direct the specific-content generation for each layer. A layer-specific prompt-enhanced module better captures detailed textual cues from the global prompt. Additionally, a self-mask guidance sampling strategy further unleashes the model's ability to generate multi-layered images. We also present a pipeline that integrates existing perceptual and generative models to produce a large dataset of high-quality, text-prompted, multi-layered images. Extensive experiments demonstrate that our LayerDiff model can generate high-quality multi-layered images with performance comparable to conventional whole-image generation methods. Moreover, LayerDiff enables a broader range of controllable generative applications, including layer-specific image editing and style transfer.

DialogGen: Multi-modal Interactive Dialogue System for Multi-turn Text-to-Image Generation

Text-to-image (T2I) generation models have significantly advanced in recent years. However, effective interaction with these models is challenging for average users due to the need for specialized prompt engineering knowledge and the inability to perform multi-turn image generation, hindering a dynamic and iterative creation process. Recent attempts have tried to equip Multi-modal Large Language Models (MLLMs) with T2I models to bring the user's natural language instructions into reality. Hence, the output modality of MLLMs is extended, and the multi-turn generation quality of T2I models is enhanced thanks to the strong multi-modal comprehension ability of MLLMs. However, many of these works face challenges in identifying correct output modalities and generating coherent images accordingly as the number of output modalities increases and the conversations go deeper. Therefore, we propose DialogGen, an effective pipeline to align off-the-shelf MLLMs and T2I models to build a Multi-modal Interactive Dialogue System (MIDS) for multi-turn Text-to-Image generation. It is composed of drawing prompt alignment, careful training data curation, and error correction. Moreover, as the field of MIDS flourishes, comprehensive benchmarks are urgently needed to evaluate MIDS fairly in terms of output modality correctness and multi-modal output coherence. To address this issue, we introduce the Multi-modal Dialogue Benchmark (DialogBen), a comprehensive bilingual benchmark designed to assess the ability of MLLMs to generate accurate and coherent multi-modal content that supports image editing. It contains two evaluation metrics to measure the model's ability to switch modalities and the coherence of the output images. Our extensive experiments on DialogBen and user study demonstrate the effectiveness of DialogGen compared with other State-of-the-Art models.

Language-Driven Visual Consensus for Zero-Shot Semantic Segmentation

The pre-trained vision-language model, exemplified by CLIP, advances zero-shot semantic segmentation by aligning visual features with class embeddings through a transformer decoder to generate semantic masks. Despite its effectiveness, prevailing methods within this paradigm encounter challenges, including overfitting on seen classes and small fragmentation in masks. To mitigate these issues, we propose a Language-Driven Visual Consensus (LDVC) approach, fostering improved alignment of semantic and visual information.Specifically, we leverage class embeddings as anchors due to their discrete and abstract nature, steering vision features toward class embeddings. Moreover, to circumvent noisy alignments from the vision part due to its redundant nature, we introduce route attention into self-attention for finding visual consensus, thereby enhancing semantic consistency within the same object. Equipped with a vision-language prompting strategy, our approach significantly boosts the generalization capacity of segmentation models for unseen classes. Experimental results underscore the effectiveness of our approach, showcasing mIoU gains of 4.5 on the PASCAL VOC 2012 and 3.6 on the COCO-Stuff 164k for unseen classes compared with the state-of-the-art methods.

NavCoT: Boosting LLM-Based Vision-and-Language Navigation via Learning Disentangled Reasoning

Vision-and-Language Navigation (VLN), as a crucial research problem of Embodied AI, requires an embodied agent to navigate through complex 3D environments following natural language instructions. Recent research has highlighted the promising capacity of large language models (LLMs) in VLN by improving navigational reasoning accuracy and interpretability. However, their predominant use in an offline manner usually suffers from substantial domain gap between the VLN task and the LLM training corpus. This paper introduces a novel strategy called Navigational Chain-of-Thought (NavCoT), where we fulfill parameter-efficient in-domain training to enable self-guided navigational decision, leading to a significant mitigation of the domain gap in a cost-effective manner. Specifically, at each timestep, the LLM is prompted to forecast the navigational chain-of-thought by: 1) acting as a world model to imagine the next observation according to the instruction, 2) selecting the candidate observation that best aligns with the imagination, and 3) determining the action based on the reasoning from the prior steps. Through constructing formalized labels for training, the LLM can learn to generate desired and reasonable chain-of-thought outputs for improving the action decision. Experimental results across various training settings and popular VLN benchmarks (e.g., Room-to-Room (R2R), Room-across-Room (RxR), Room-for-Room (R4R)) show the significant superiority of NavCoT over the direct action prediction variants. Through simple parameter-efficient finetuning, our NavCoT outperforms a recent GPT4-based approach with ~7% relative improvement on the R2R dataset. We believe that NavCoT will help unlock more task-adaptive and scalable LLM-based embodied agents, which are helpful for developing real-world robotics applications. Code is available at https://github.com/expectorlin/NavCoT.

Towards Deviation-Robust Agent Navigation via Perturbation-Aware Contrastive Learning

Vision-and-language navigation (VLN) asks an agent to follow a given language instruction to navigate through a real 3D environment. Despite significant advances, conventional VLN agents are trained typically under disturbance-free environments and may easily fail in real-world scenarios, since they are unaware of how to deal with various possible disturbances, such as sudden obstacles or human interruptions, which widely exist and may usually cause an unexpected route deviation. In this paper, we present a model-agnostic training paradigm, called Progressive Perturbation-aware Contrastive Learning (PROPER) to enhance the generalization ability of existing VLN agents, by requiring them to learn towards deviation-robust navigation. Specifically, a simple yet effective path perturbation scheme is introduced to implement the route deviation, with which the agent is required to still navigate successfully following the original instruction. Since directly enforcing the agent to learn perturbed trajectories may lead to inefficient training, a progressively perturbed trajectory augmentation strategy is designed, where the agent can self-adaptively learn to navigate under perturbation with the improvement of its navigation performance for each specific trajectory. For encouraging the agent to well capture the difference brought by perturbation, a perturbation-aware contrastive learning mechanism is further developed by contrasting perturbation-free trajectory encodings and perturbation-based counterparts. Extensive experiments on R2R show that PROPER can benefit multiple VLN baselines in perturbation-free scenarios. We further collect the perturbed path data to construct an introspection subset based on the R2R, called Path-Perturbed R2R (PP-R2R). The results on PP-R2R show unsatisfying robustness of popular VLN agents and the capability of PROPER in improving the navigation robustness.

DNA Family: Boosting Weight-Sharing NAS with Block-Wise Supervisions

Neural Architecture Search (NAS), aiming at automatically designing neural architectures by machines, has been considered a key step toward automatic machine learning. One notable NAS branch is the weight-sharing NAS, which significantly improves search efficiency and allows NAS algorithms to run on ordinary computers. Despite receiving high expectations, this category of methods suffers from low search effectiveness. By employing a generalization boundedness tool, we demonstrate that the devil behind this drawback is the untrustworthy architecture rating with the oversized search space of the possible architectures. Addressing this problem, we modularize a large search space into blocks with small search spaces and develop a family of models with the distilling neural architecture (DNA) techniques. These proposed models, namely a DNA family, are capable of resolving multiple dilemmas of the weight-sharing NAS, such as scalability, efficiency, and multi-modal compatibility. Our proposed DNA models can rate all architecture candidates, as opposed to previous works that can only access a subsearch space using heuristic algorithms. Moreover, under a certain computational complexity constraint, our method can seek architectures with different depths and widths. Extensive experimental evaluations show that our models achieve state-of-the-art top-1 accuracy of 78.9% and 83.6% on ImageNet for a mobile convolutional network and a small vision transformer, respectively. Additionally, we provide in-depth empirical analysis and insights into neural architecture ratings. Codes available: \url{https://github.com/changlin31/DNA}.

AlignMiF: Geometry-Aligned Multimodal Implicit Field for LiDAR-Camera Joint Synthesis

Neural implicit fields have been a de facto standard in novel view synthesis. Recently, there exist some methods exploring fusing multiple modalities within a single field, aiming to share implicit features from different modalities to enhance reconstruction performance. However, these modalities often exhibit misaligned behaviors: optimizing for one modality, such as LiDAR, can adversely affect another, like camera performance, and vice versa. In this work, we conduct comprehensive analyses on the multimodal implicit field of LiDAR-camera joint synthesis, revealing the underlying issue lies in the misalignment of different sensors. Furthermore, we introduce AlignMiF, a geometrically aligned multimodal implicit field with two proposed modules: Geometry-Aware Alignment (GAA) and Shared Geometry Initialization (SGI). These modules effectively align the coarse geometry across different modalities, significantly enhancing the fusion process between LiDAR and camera data. Through extensive experiments across various datasets and scenes, we demonstrate the effectiveness of our approach in facilitating better interaction between LiDAR and camera modalities within a unified neural field. Specifically, our proposed AlignMiF, achieves remarkable improvement over recent implicit fusion methods (+2.01 and +3.11 image PSNR on the KITTI-360 and Waymo datasets) and consistently surpasses single modality performance (13.8% and 14.2% reduction in LiDAR Chamfer Distance on the respective datasets).

MUSTARD: Mastering Uniform Synthesis of Theorem and Proof Data

Recent large language models (LLMs) have witnessed significant advancement in various tasks, including mathematical reasoning and theorem proving. As these two tasks require strict and formal multi-step inference, they are appealing domains for exploring the reasoning ability of LLMs but still face important challenges. Previous studies such as Chain-of-Thought (CoT) have revealed the effectiveness of intermediate steps guidance. However, such step-wise annotation requires heavy labor, leading to insufficient training steps for current benchmarks. To fill this gap, this work introduces MUSTARD, a data generation framework that masters uniform synthesis of theorem and proof data of high quality and diversity. MUSTARD synthesizes data in three stages: (1) It samples a few mathematical concept seeds as the problem category. (2) Then, it prompts a generative language model with the sampled concepts to obtain both the problems and their step-wise formal solutions. (3) Lastly, the framework utilizes a proof assistant (e.g., Lean Prover) to filter the valid proofs. With the proposed MUSTARD, we present a theorem-and-proof benchmark MUSTARDSAUCE with 5,866 valid data points. Each data point contains an informal statement, an informal proof, and a translated formal proof that passes the prover validation. We perform extensive analysis and demonstrate that MUSTARD generates validated high-quality step-by-step data. We further apply the MUSTARDSAUCE for fine-tuning smaller language models. The fine-tuned Llama 2-7B achieves a 15.41% average relative performance gain in automated theorem proving, and 8.18% in math word problems. Codes and data are available at https://github.com/Eleanor-H/MUSTARD.