Abstract:Generalized Category Discovery (GCD) aims to identify a mix of known and novel categories within unlabeled data sets, providing a more realistic setting for image recognition. Essentially, GCD needs to remember existing patterns thoroughly to recognize novel categories. Recent state-of-the-art method SimGCD transfers the knowledge from known-class data to the learning of novel classes through debiased learning. However, some patterns are catastrophically forgot during adaptation and thus lead to poor performance in novel categories classification. To address this issue, we propose a novel learning approach, LegoGCD, which is seamlessly integrated into previous methods to enhance the discrimination of novel classes while maintaining performance on previously encountered known classes. Specifically, we design two types of techniques termed as Local Entropy Regularization (LER) and Dual-views Kullback Leibler divergence constraint (DKL). The LER optimizes the distribution of potential known class samples in unlabeled data, thus ensuring the preservation of knowledge related to known categories while learning novel classes. Meanwhile, DKL introduces Kullback Leibler divergence to encourage the model to produce a similar prediction distribution of two view samples from the same image. In this way, it successfully avoids mismatched prediction and generates more reliable potential known class samples simultaneously. Extensive experiments validate that the proposed LegoGCD effectively addresses the known category forgetting issue across all datasets, eg, delivering a 7.74% and 2.51% accuracy boost on known and novel classes in CUB, respectively. Our code is available at: https://github.com/Cliffia123/LegoGCD.
Abstract:Recent Multimodal Large Language Models (MLLMs) have typically focused on integrating visual and textual modalities, with less emphasis placed on the role of speech in enhancing interaction. However, speech plays a crucial role in multimodal dialogue systems, and implementing high-performance in both vision and speech tasks remains a significant challenge due to the fundamental modality differences. In this paper, we propose a carefully designed multi-stage training methodology that progressively trains LLM to understand both visual and speech information, ultimately enabling fluent vision and speech interaction. Our approach not only preserves strong vision-language capacity, but also enables efficient speech-to-speech dialogue capabilities without separate ASR and TTS modules, significantly accelerating multimodal end-to-end response speed. By comparing our method against state-of-the-art counterparts across benchmarks for image, video, and speech tasks, we demonstrate that our model is equipped with both strong visual and speech capabilities, making near real-time vision and speech interaction.
Abstract:Semi-supervised learning (SSL) assumes that neighbor points lie in the same category (neighbor assumption), and points in different clusters belong to various categories (cluster assumption). Existing methods usually rely on similarity measures to retrieve the similar neighbor points, ignoring cluster assumption, which may not utilize unlabeled information sufficiently and effectively. This paper first provides a systematical investigation into the significant role of probability density in SSL and lays a solid theoretical foundation for cluster assumption. To this end, we introduce a Probability-Density-Aware Measure (PM) to discern the similarity between neighbor points. To further improve Label Propagation, we also design a Probability-Density-Aware Measure Label Propagation (PMLP) algorithm to fully consider the cluster assumption in label propagation. Last but not least, we prove that traditional pseudo-labeling could be viewed as a particular case of PMLP, which provides a comprehensive theoretical understanding of PMLP's superior performance. Extensive experiments demonstrate that PMLP achieves outstanding performance compared with other recent methods.
Abstract:Knowledge distillation (KD) is a valuable yet challenging approach that enhances a compact student network by learning from a high-performance but cumbersome teacher model. However, previous KD methods for image restoration overlook the state of the student during the distillation, adopting a fixed solution space that limits the capability of KD. Additionally, relying solely on L1-type loss struggles to leverage the distribution information of images. In this work, we propose a novel dynamic contrastive knowledge distillation (DCKD) framework for image restoration. Specifically, we introduce dynamic contrastive regularization to perceive the student's learning state and dynamically adjust the distilled solution space using contrastive learning. Additionally, we also propose a distribution mapping module to extract and align the pixel-level category distribution of the teacher and student models. Note that the proposed DCKD is a structure-agnostic distillation framework, which can adapt to different backbones and can be combined with methods that optimize upper-bound constraints to further enhance model performance. Extensive experiments demonstrate that DCKD significantly outperforms the state-of-the-art KD methods across various image restoration tasks and backbones.
Abstract:Despite a big leap forward in capability, multimodal large language models (MLLMs) tend to behave like a sloth in practical use, i.e., slow response and large latency. Recent efforts are devoted to building tiny MLLMs for better efficiency, but the plethora of visual tokens still used limit their actual speedup. In this paper, we propose a powerful and fast tiny MLLM called FlashSloth. Different from previous efforts, FlashSloth focuses on improving the descriptive power of visual tokens in the process of compressing their redundant semantics. In particular, FlashSloth introduces embedded visual compression designs to capture both visually salient and instruction-related image information, so as to achieving superior multimodal performance with fewer visual tokens. Extensive experiments are conducted to validate the proposed FlashSloth, and a bunch of tiny but strong MLLMs are also comprehensively compared, e.g., InternVL2, MiniCPM-V2 and Qwen2-VL. The experimental results show that compared with these advanced tiny MLLMs, our FlashSloth can greatly reduce the number of visual tokens, training memory and computation complexity while retaining high performance on various VL tasks.
Abstract:Multimodal Large Language Models (MLLMs) have achieved remarkable success in vision understanding, reasoning, and interaction. However, the inference computation and memory increase progressively with the generation of output tokens during decoding, directly affecting the efficacy of MLLMs. Existing methods attempt to reduce the vision context redundancy to achieve efficient MLLMs. Unfortunately, the efficiency benefits of the vision context reduction in the prefill stage gradually diminish during the decoding stage. To address this problem, we proposed a dynamic vision-language context sparsification framework Dynamic-LLaVA, which dynamically reduces the redundancy of vision context in the prefill stage and decreases the memory and computation overhead of the generated language context during decoding. Dynamic-LLaVA designs a tailored sparsification inference scheme for different inference modes, i.e., prefill, decoding with and without KV cache, to achieve efficient inference of MLLMs. In practice, Dynamic-LLaVA can reduce computation consumption by $\sim$75\% in the prefill stage. Meanwhile, throughout the entire generation process of MLLMs, Dynamic-LLaVA reduces the $\sim$50\% computation consumption under decoding without KV cache, while saving $\sim$50\% GPU memory overhead when decoding with KV cache, due to the vision-language context sparsification. Extensive experiments also demonstrate that Dynamic-LLaVA achieves efficient inference for MLLMs with negligible understanding and generation ability degradation or even performance gains compared to the full-context inference baselines. Code is available at https://github.com/Osilly/dynamic_llava .
Abstract:The success of Multimodal Large Language Models (MLLMs) in the image domain has garnered wide attention from the research community. Drawing on previous successful experiences, researchers have recently explored extending the success to the video understanding realms. Apart from training from scratch, an efficient way is to utilize the pre-trained image-LLMs, leading to two mainstream approaches, i.e. zero-shot inference and further fine-tuning with video data. In this work, our study of these approaches harvests an effective data augmentation method. We first make a deeper inspection of the zero-shot inference way and identify two limitations, i.e. limited generalization and lack of temporal understanding capabilities. Thus, we further investigate the fine-tuning approach and find a low learning efficiency when simply using all the video data samples, which can be attributed to a lack of instruction diversity. Aiming at this issue, we develop a method called T2Vid to synthesize video-like samples to enrich the instruction diversity in the training corpus. Integrating these data enables a simple and efficient training scheme, which achieves performance comparable to or even superior to using full video datasets by training with just 15% the sample size. Meanwhile, we find that the proposed scheme can boost the performance of long video understanding without training with long video samples. We hope our study will spark more thinking about using MLLMs for video understanding and curation of high-quality data. The code is released at https://github.com/xjtupanda/T2Vid.
Abstract:Blind image quality assessment (BIQA) serves as a fundamental task in computer vision, yet it often fails to consistently align with human subjective perception. Recent advances show that multi-scale evaluation strategies are promising due to their ability to replicate the hierarchical structure of human vision. However, the effectiveness of these strategies is limited by a lack of understanding of how different image scales influence perceived quality. This paper addresses two primary challenges: the significant redundancy of information across different scales, and the confusion caused by combining features from these scales, which may vary widely in quality. To this end, a new multi-scale BIQA framework is proposed, namely Contrast-Constrained Scale-Focused IQA Framework (CSFIQA). CSFIQA features a selective focus attention mechanism to minimize information redundancy and highlight critical quality-related information. Additionally, CSFIQA includes a scale-level contrastive learning module equipped with a noise sample matching mechanism to identify quality discrepancies across the same image content at different scales. By exploring the intrinsic relationship between image scales and the perceived quality, the proposed CSFIQA achieves leading performance on eight benchmark datasets, e.g., achieving SRCC values of 0.967 (versus 0.947 in CSIQ) and 0.905 (versus 0.876 in LIVEC).
Abstract:The remarkable multimodal capabilities and interactive experience of GPT-4o underscore their necessity in practical applications, yet open-source models rarely excel in both areas. In this paper, we introduce VITA, the first-ever open-source Multimodal Large Language Model (MLLM) adept at simultaneous processing and analysis of Video, Image, Text, and Audio modalities, and meanwhile has an advanced multimodal interactive experience. Starting from Mixtral 8x7B as a language foundation, we expand its Chinese vocabulary followed by bilingual instruction tuning. We further endow the language model with visual and audio capabilities through two-stage multi-task learning of multimodal alignment and instruction tuning. VITA demonstrates robust foundational capabilities of multilingual, vision, and audio understanding, as evidenced by its strong performance across a range of both unimodal and multimodal benchmarks. Beyond foundational capabilities, we have made considerable progress in enhancing the natural multimodal human-computer interaction experience. To the best of our knowledge, we are the first to exploit non-awakening interaction and audio interrupt in MLLM. VITA is the first step for the open-source community to explore the seamless integration of multimodal understanding and interaction. While there is still lots of work to be done on VITA to get close to close-source counterparts, we hope that its role as a pioneer can serve as a cornerstone for subsequent research. Project Page: https://vita-home.github.io.
Abstract:Most WSOD methods rely on traditional object proposals to generate candidate regions and are confronted with unstable training, which easily gets stuck in a poor local optimum. In this paper, we introduce a unified, high-capacity weakly supervised object detection (WSOD) network called HUWSOD, which utilizes a comprehensive self-training framework without needing external modules or additional supervision. HUWSOD innovatively incorporates a self-supervised proposal generator and an autoencoder proposal generator with a multi-rate resampling pyramid to replace traditional object proposals, enabling end-to-end WSOD training and inference. Additionally, we implement a holistic self-training scheme that refines detection scores and coordinates through step-wise entropy minimization and consistency-constraint regularization, ensuring consistent predictions across stochastic augmentations of the same image. Extensive experiments on PASCAL VOC and MS COCO demonstrate that HUWSOD competes with state-of-the-art WSOD methods, eliminating the need for offline proposals and additional data. The peak performance of HUWSOD approaches that of fully-supervised Faster R-CNN. Our findings also indicate that randomly initialized boxes, although significantly different from well-designed offline object proposals, are effective for WSOD training.