Text-to-image diffusion models are gradually introduced into computer graphics, recently enabling the development of Text-to-3D pipelines in an open domain. However, for interactive editing purposes, local manipulations of content through a simplistic textual interface can be arduous. Incorporating user guided sketches with Text-to-image pipelines offers users more intuitive control. Still, as state-of-the-art Text-to-3D pipelines rely on optimizing Neural Radiance Fields (NeRF) through gradients from arbitrary rendering views, conditioning on sketches is not straightforward. In this paper, we present SKED, a technique for editing 3D shapes represented by NeRFs. Our technique utilizes as few as two guiding sketches from different views to alter an existing neural field. The edited region respects the prompt semantics through a pre-trained diffusion model. To ensure the generated output adheres to the provided sketches, we propose novel loss functions to generate the desired edits while preserving the density and radiance of the base instance. We demonstrate the effectiveness of our proposed method through several qualitative and quantitative experiments.
Structure prediction tasks such as event extraction require an in-depth understanding of the output structure and sub-task dependencies, thus they still heavily rely on task-specific training data to obtain reasonable performance. Due to the high cost of human annotation, low-resource event extraction, which requires minimal human cost, is urgently needed in real-world information extraction applications. We propose to synthesize data instances given limited seed demonstrations to boost low-resource event extraction performance. We propose STAR, a structure-to-text data generation method that first generates complicated event structures (Y) and then generates input passages (X), all with Large Language Models. We design fine-grained step-by-step instructions and the error cases and quality issues identified through self-reflection can be self-refined. Our experiments indicate that data generated by STAR can significantly improve the low-resource event extraction performance and they are even more effective than human-curated data points in some cases.
Referring video object segmentation (RVOS) aims at segmenting an object in a video following human instruction. Current state-of-the-art methods fall into an offline pattern, in which each clip independently interacts with text embedding for cross-modal understanding. They usually present that the offline pattern is necessary for RVOS, yet model limited temporal association within each clip. In this work, we break up the previous offline belief and propose a simple yet effective online model using explicit query propagation, named OnlineRefer. Specifically, our approach leverages target cues that gather semantic information and position prior to improve the accuracy and ease of referring predictions for the current frame. Furthermore, we generalize our online model into a semi-online framework to be compatible with video-based backbones. To show the effectiveness of our method, we evaluate it on four benchmarks, \ie, Refer-Youtube-VOS, Refer-DAVIS17, A2D-Sentences, and JHMDB-Sentences. Without bells and whistles, our OnlineRefer with a Swin-L backbone achieves 63.5 J&F and 64.8 J&F on Refer-Youtube-VOS and Refer-DAVIS17, outperforming all other offline methods.
Cross-domain text classification aims to adapt models to a target domain that lacks labeled data. It leverages or reuses rich labeled data from the different but related source domain(s) and unlabeled data from the target domain. To this end, previous work focuses on either extracting domain-invariant features or task-agnostic features, ignoring domain-aware features that may be present in the target domain and could be useful for the downstream task. In this paper, we propose a two-stage framework for cross-domain text classification. In the first stage, we finetune the model with mask language modeling (MLM) and labeled data from the source domain. In the second stage, we further fine-tune the model with self-supervised distillation (SSD) and unlabeled data from the target domain. We evaluate its performance on a public cross-domain text classification benchmark and the experiment results show that our method achieves new state-of-the-art results for both single-source domain adaptations (94.17% $\uparrow$1.03%) and multi-source domain adaptations (95.09% $\uparrow$1.34%).
We introduce Cap3D, an automatic approach for generating descriptive text for 3D objects. This approach utilizes pretrained models from image captioning, image-text alignment, and LLM to consolidate captions from multiple views of a 3D asset, completely side-stepping the time-consuming and costly process of manual annotation. We apply Cap3D to the recently introduced large-scale 3D dataset, Objaverse, resulting in 660k 3D-text pairs. Our evaluation, conducted using 41k human annotations from the same dataset, demonstrates that Cap3D surpasses human-authored descriptions in terms of quality, cost, and speed. Through effective prompt engineering, Cap3D rivals human performance in generating geometric descriptions on 17k collected annotations from the ABO dataset. Finally, we finetune Text-to-3D models on Cap3D and human captions, and show Cap3D outperforms; and benchmark the SOTA including Point-E, Shape-E, and DreamFusion.
In this paper, we present a new text-guided 3D shape generation approach (ISS++) that uses images as a stepping stone to bridge the gap between text and shape modalities for generating 3D shapes without requiring paired text and 3D data. The core of our approach is a two-stage feature-space alignment strategy that leverages a pre-trained single-view reconstruction (SVR) model to map CLIP features to shapes: to begin with, map the CLIP image feature to the detail-rich 3D shape space of the SVR model, then map the CLIP text feature to the 3D shape space through encouraging the CLIP-consistency between rendered images and the input text. Besides, to extend beyond the generative capability of the SVR model, we design a text-guided 3D shape stylization module that can enhance the output shapes with novel structures and textures. Further, we exploit pre-trained text-to-image diffusion models to enhance the generative diversity, fidelity, and stylization capability. Our approach is generic, flexible, and scalable, and it can be easily integrated with various SVR models to expand the generative space and improve the generative fidelity. Extensive experimental results demonstrate that our approach outperforms the state-of-the-art methods in terms of generative quality and consistency with the input text. Codes and models are released at https://github.com/liuzhengzhe/ISS-Image-as-Stepping-Stone-for-Text-Guided-3D-Shape-Generation.
Text-guided image generation has witnessed unprecedented progress due to the development of diffusion models. Beyond text and image, sound is a vital element within the sphere of human perception, offering vivid representations and naturally coinciding with corresponding scenes. Taking advantage of sound therefore presents a promising avenue for exploration within image generation research. However, the relationship between audio and image supervision remains significantly underdeveloped, and the scarcity of related, high-quality datasets brings further obstacles. In this paper, we propose a unified framework 'Align, Adapt, and Inject' (AAI) for sound-guided image generation, editing, and stylization. In particular, our method adapts input sound into a sound token, like an ordinary word, which can plug and play with existing powerful diffusion-based Text-to-Image (T2I) models. Specifically, we first train a multi-modal encoder to align audio representation with the pre-trained textual manifold and visual manifold, respectively. Then, we propose the audio adapter to adapt audio representation into an audio token enriched with specific semantics, which can be injected into a frozen T2I model flexibly. In this way, we are able to extract the dynamic information of varied sounds, while utilizing the formidable capability of existing T2I models to facilitate sound-guided image generation, editing, and stylization in a convenient and cost-effective manner. The experiment results confirm that our proposed AAI outperforms other text and sound-guided state-of-the-art methods. And our aligned multi-modal encoder is also competitive with other approaches in the audio-visual retrieval and audio-text retrieval tasks.
Evaluating the factuality of long-form text generated by large language models (LMs) is non-trivial because (1) generations often contain a mixture of supported and unsupported pieces of information, making binary judgments of quality inadequate, and (2) human evaluation is time-consuming and costly. In this paper, we introduce FActScore (Factual precision in Atomicity Score), a new evaluation that breaks a generation into a series of atomic facts and computes the percentage of atomic facts supported by a reliable knowledge source. We conduct an extensive human evaluation to obtain FActScores of people biographies generated by several state-of-the-art commercial LMs -- InstructGPT, ChatGPT, and the retrieval-augmented PerplexityAI -- and report new analysis demonstrating the need for such a fine-grained score (e.g., ChatGPT only achieves 58%). Since human evaluation is costly, we also introduce an automated model that estimates FActScore, using retrieval and a strong language model, with less than a 2% error rate. Finally, we use this automated metric to evaluate 6,500 generations from a new set of 13 recent LMs that would have cost $26K if evaluated by humans, with various findings: GPT-4 and ChatGPT are more factual than public models, and Vicuna and Alpaca are some of the best public models.
We study how vision-language models trained on Internet-scale data can be incorporated directly into end-to-end robotic control to boost generalization and enable emergent semantic reasoning. Our goal is to enable a single end-to-end trained model to both learn to map robot observations to actions and enjoy the benefits of large-scale pretraining on language and vision-language data from the web. To this end, we propose to co-fine-tune state-of-the-art vision-language models on both robotic trajectory data and Internet-scale vision-language tasks, such as visual question answering. In contrast to other approaches, we propose a simple, general recipe to achieve this goal: in order to fit both natural language responses and robotic actions into the same format, we express the actions as text tokens and incorporate them directly into the training set of the model in the same way as natural language tokens. We refer to such category of models as vision-language-action models (VLA) and instantiate an example of such a model, which we call RT-2. Our extensive evaluation (6k evaluation trials) shows that our approach leads to performant robotic policies and enables RT-2 to obtain a range of emergent capabilities from Internet-scale training. This includes significantly improved generalization to novel objects, the ability to interpret commands not present in the robot training data (such as placing an object onto a particular number or icon), and the ability to perform rudimentary reasoning in response to user commands (such as picking up the smallest or largest object, or the one closest to another object). We further show that incorporating chain of thought reasoning allows RT-2 to perform multi-stage semantic reasoning, for example figuring out which object to pick up for use as an improvised hammer (a rock), or which type of drink is best suited for someone who is tired (an energy drink).
The visual-question localized-answering (VQLA) system can serve as a knowledgeable assistant in surgical education. Except for providing text-based answers, the VQLA system can highlight the interested region for better surgical scene understanding. However, deep neural networks (DNNs) suffer from catastrophic forgetting when learning new knowledge. Specifically, when DNNs learn on incremental classes or tasks, their performance on old tasks drops dramatically. Furthermore, due to medical data privacy and licensing issues, it is often difficult to access old data when updating continual learning (CL) models. Therefore, we develop a non-exemplar continual surgical VQLA framework, to explore and balance the rigidity-plasticity trade-off of DNNs in a sequential learning paradigm. We revisit the distillation loss in CL tasks, and propose rigidity-plasticity-aware distillation (RP-Dist) and self-calibrated heterogeneous distillation (SH-Dist) to preserve the old knowledge. The weight aligning (WA) technique is also integrated to adjust the weight bias between old and new tasks. We further establish a CL framework on three public surgical datasets in the context of surgical settings that consist of overlapping classes between old and new surgical VQLA tasks. With extensive experiments, we demonstrate that our proposed method excellently reconciles learning and forgetting on the continual surgical VQLA over conventional CL methods. Our code is publicly accessible.