LLaVA-UHD: an LMM Perceiving Any Aspect Ratio and High-Resolution Images

Visual encoding constitutes the basis of large multimodal models (LMMs) in understanding the visual world. Conventional LMMs process images in fixed sizes and limited resolutions, while recent explorations in this direction are limited in adaptivity, efficiency, and even correctness. In this work, we first take GPT-4V and LLaVA-1.5 as representative examples and expose systematic flaws rooted in their visual encoding strategy. To address the challenges, we present LLaVA-UHD, a large multimodal model that can efficiently perceive images in any aspect ratio and high resolution. LLaVA-UHD includes three key components: (1) An image modularization strategy that divides native-resolution images into smaller variable-sized slices for efficient and extensible encoding, (2) a compression module that further condenses image tokens from visual encoders, and (3) a spatial schema to organize slice tokens for LLMs. Comprehensive experiments show that LLaVA-UHD outperforms established LMMs trained with 2-3 orders of magnitude more data on 9 benchmarks. Notably, our model built on LLaVA-1.5 336x336 supports 6 times larger (i.e., 672x1088) resolution images using only 94% inference computation, and achieves 6.4 accuracy improvement on TextVQA. Moreover, the model can be efficiently trained in academic settings, within 23 hours on 8 A100 GPUs (vs. 26 hours of LLaVA-1.5). We make the data and code publicly available at https://github.com/thunlp/LLaVA-UHD.

Controllable Dense Captioner with Multimodal Embedding Bridging

In this paper, we propose a controllable dense captioner (ControlCap), which accommodates user's intention to dense captioning by introducing linguistic guidance. ControlCap is defined as a multimodal embedding bridging architecture, which comprises multimodal embedding generation (MEG) module and bi-directional embedding bridging (BEB) module. While MEG module represents objects/regions by combining embeddings of detailed information with context-aware ones, it also endows ControlCap the adaptability to specialized controls by utilizing them as linguistic guidance. BEB module aligns the linguistic guidance with visual embeddings through borrowing/returning features from/to the visual domain and gathering such features to predict text descriptions. Experiments on Visual Genome and VG-COCO datasets show that ControlCap respectively outperforms the state-of-the-art methods by 1.5% and 3.7% (mAP). Last but not least, with the capability of converting region-category pairs to region-text pairs, ControlCap is able to act as a powerful data engine for dense captioning. Code is available at https://github.com/callsys/ControlCap.

Bidirectional Feature Globalization for Few-shot Semantic Segmentation of 3D Point Cloud Scenes

Few-shot segmentation of point cloud remains a challenging task, as there is no effective way to convert local point cloud information to global representation, which hinders the generalization ability of point features. In this study, we propose a bidirectional feature globalization (BFG) approach, which leverages the similarity measurement between point features and prototype vectors to embed global perception to local point features in a bidirectional fashion. With point-to-prototype globalization (Po2PrG), BFG aggregates local point features to prototypes according to similarity weights from dense point features to sparse prototypes. With prototype-to-point globalization (Pr2PoG), the global perception is embedded to local point features based on similarity weights from sparse prototypes to dense point features. The sparse prototypes of each class embedded with global perception are summarized to a single prototype for few-shot 3D segmentation based on the metric learning framework. Extensive experiments on S3DIS and ScanNet demonstrate that BFG significantly outperforms the state-of-the-art methods.

Integral Migrating Pre-trained Transformer Encoder-decoders for Visual Object Detection

Modern object detectors have taken the advantages of pre-trained vision transformers by using them as backbone networks. However, except for the backbone networks, other detector components, such as the detector head and the feature pyramid network, remain randomly initialized, which hinders the consistency between detectors and pre-trained models. In this study, we propose to integrally migrate the pre-trained transformer encoder-decoders (imTED) for object detection, constructing a feature extraction-operation path that is not only "fully pre-trained" but also consistent with pre-trained models. The essential improvements of imTED over existing transformer-based detectors are twofold: (1) it embeds the pre-trained transformer decoder to the detector head; and (2) it removes the feature pyramid network from the feature extraction path. Such improvements significantly reduce the proportion of randomly initialized parameters and enhance the generation capability of detectors. Experiments on MS COCO dataset demonstrate that imTED consistently outperforms its counterparts by ~2.8% AP. Without bells and whistles, imTED improves the state-of-the-art of few-shot object detection by up to 7.6% AP, demonstrating significantly higher generalization capability. Code will be made publicly available.

Semantic Segmentation for Point Cloud Scenes via Dilated Graph Feature Aggregation and Pyramid Decoders

Semantic segmentation of point clouds generates comprehensive understanding of scenes through densely predicting the category for each point. Due to the unicity of receptive field, semantic segmentation of point clouds remains challenging for the expression of multi-receptive field features, which brings about the misclassification of instances with similar spatial structures. In this paper, we propose a graph convolutional network DGFA-Net rooted in dilated graph feature aggregation (DGFA), guided by multi-basis aggregation loss (MALoss) calculated through Pyramid Decoders. To configure multi-receptive field features, DGFA which takes the proposed dilated graph convolution (DGConv) as its basic building block, is designed to aggregate multi-scale feature representation by capturing dilated graphs with various receptive regions. By simultaneously considering penalizing the receptive field information with point sets of different resolutions as calculation bases, we introduce Pyramid Decoders driven by MALoss for the diversity of receptive field bases. Combining these two aspects, DGFA-Net significantly improves the segmentation performance of instances with similar spatial structures. Experiments on S3DIS, ShapeNetPart and Toronto-3D show that DGFA-Net outperforms the baseline approach, achieving a new state-of-the-art segmentation performance.

Long-tailed Distribution Adaptation

Recognizing images with long-tailed distributions remains a challenging problem while there lacks an interpretable mechanism to solve this problem. In this study, we formulate Long-tailed recognition as Domain Adaption (LDA), by modeling the long-tailed distribution as an unbalanced domain and the general distribution as a balanced domain. Within the balanced domain, we propose to slack the generalization error bound, which is defined upon the empirical risks of unbalanced and balanced domains and the divergence between them. We propose to jointly optimize empirical risks of the unbalanced and balanced domains and approximate their domain divergence by intra-class and inter-class distances, with the aim to adapt models trained on the long-tailed distribution to general distributions in an interpretable way. Experiments on benchmark datasets for image recognition, object detection, and instance segmentation validate that our LDA approach, beyond its interpretability, achieves state-of-the-art performance. Code is available at https://github.com/pengzhiliang/LDA.