Natural images often exhibit underlying sparse structures, with information density varying significantly across different spatial locations. However, most generative models rely on dense grid-based pixels or latents, neglecting this inherent sparsity. In this paper, we explore modeling visual generation paradigm via sparse non-grid latent representations. Specifically, we design a sparse autoencoder that represents an image as a small number of latents with their positional properties (i.e., regions of interest, RoIs) with high reconstruction quality. We then explore training flow-matching transformers jointly on non-grid latents and RoI values. To the best knowledge, we are the first to address spatial sparsity using RoIs in generative process. Experimental results show that our sparse flow-based transformers have competitive performance compared with dense grid-based counterparts with significantly reduced lower compute, and reaches a competitive 2.76 FID with just 64 latents on class-conditional ImageNet $256\times 256$ generation.

Recent Large Language Models (LLMs) have been en-hanced with vision capabilities, enabling them to compre-hend images, videos, and interleaved vision-language con-tent. However, the learning methods of these large multi-modal models (LMMs) typically treat videos as predeter-mined clips, rendering them less effective and efficient at handling streaming video inputs. In this paper, we pro-pose a novel Learning-In- Video-Stream (LIVE) framework, which enables temporally aligned, long-context, and real-time dialogue within a continuous video stream. Our LIVE framework comprises comprehensive approaches to achieve video streaming dialogue, encompassing: (1) a training ob-jective designed to perform language modeling for contin-uous streaming inputs, (2) a data generation scheme that converts offline temporal annotations into a streaming di-alogue format, and (3) an optimized inference pipeline to speed up interactive chat in real-world video streams. With our LIVE framework, we develop a simplified model called VideoLLM-online and demonstrate its significant advan-tages in processing streaming videos. For instance, our VideoLLM-online-7B model can operate at over 10 FPS on an A100 GPU for a 5-minute video clip from Ego4D narration. Moreover, VideoLLM-online also showcases state-of-the-art performance on public offline video bench-marks, such as recognition, captioning, and forecasting. The code, model, data, and demo have been made available at showlab.github. iolvideollm-online.

The recently proposed SparseFormer architecture provides an alternative approach to visual understanding by utilizing a significantly lower number of visual tokens via adjusting RoIs, greatly reducing computational costs while still achieving promising performance. However, training SparseFormers from scratch is still expensive, and scaling up the number of parameters can be challenging. In this paper, we propose to bootstrap SparseFormers from ViT-based vision foundation models in a simple and efficient way. Since the majority of SparseFormer blocks are the standard transformer ones, we can inherit weights from large-scale pre-trained vision transformers and freeze them as much as possible. Therefore, we only need to train the SparseFormer-specific lightweight focusing transformer to adjust token RoIs and fine-tune a few early pre-trained blocks to align the final token representation. In such a way, we can bootstrap SparseFormer architectures from various large-scale pre-trained models (e.g., IN-21 K pre-trained AugRegs or CLIPs) using a rather smaller amount of training samples (e.g., IN-IK) and without labels or captions within just a few hours. As a result, the bootstrapped unimodal SparseFormer (from AugReg-ViT-L/16-384) can reach 84.9% accuracy on IN-IK with only 49 tokens, and the multimodal SparseFormer from CLIPs also demonstrates notable zero-shot performance with highly reduced computational cost without seeing any caption during the bootstrapping procedure. In addition, CLIP-bootstrapped SparseFormers, which align the output space with language without seeing a word, can serve as efficient vision encoders in multimodal large language models. Code and models are available at https://github.com/showlab/sparseformer

Human visual recognition is a sparse process, where only a few salient visual cues are attended to rather than every detail being traversed uniformly. However, most current vision networks follow a dense paradigm, processing every single visual unit (such as pixels or patches) in a uniform manner. In this paper, we challenge this dense convention and present a new vision transformer, coined SparseFormer, to explicitly imitate human's sparse visual recognition in an end-to-end manner. SparseFormer learns to represent images using a highly limited number of tokens (e.g., down to $9$) in the latent space with sparse feature sampling procedure instead of processing dense units in the original image space. Therefore, SparseFormer circumvents most of dense operations on the image space and has much lower computational costs. Experiments on the ImageNet-1K classification show that SparseFormer delivers performance on par with canonical or well-established models while offering more favorable accuracy-throughput tradeoff. Moreover, the design of our network can be easily extended to the video classification task with promising performance with lower compute. We hope our work can provide an alternative way for visual modeling and inspire further research on sparse vision architectures. Code and weights are available at https://github.com/showlab/sparseformer.

We introduce VideoLISA, a video-based multimodal large language model designed to tackle the problem of language-instructed reasoning segmentation in videos. Leveraging the reasoning capabilities and world knowledge of large language models, and augmented by the Segment Anything Model, VideoLISA generates temporally consistent segmentation masks in videos based on language instructions. Existing image-based methods, such as LISA, struggle with video tasks due to the additional temporal dimension, which requires temporal dynamic understanding and consistent segmentation across frames. VideoLISA addresses these challenges by integrating a Sparse Dense Sampling strategy into the video-LLM, which balances temporal context and spatial detail within computational constraints. Additionally, we propose a One-Token-Seg-All approach using a specially designed <TRK> token, enabling the model to segment and track objects across multiple frames. Extensive evaluations on diverse benchmarks, including our newly introduced ReasonVOS benchmark, demonstrate VideoLISA's superior performance in video object segmentation tasks involving complex reasoning, temporal understanding, and object tracking. While optimized for videos, VideoLISA also shows promising generalization to image segmentation, revealing its potential as a unified foundation model for language-instructed object segmentation. Code and model will be available at: https://github.com/showlab/VideoLISA.

Traditional video action detectors typically adopt the two-stage pipeline, where a person detector is first employed to generate actor boxes and then 3D RoIAlign is used to extract actor-specific features for action recognition. This detection paradigm requires multi-stage training and inference, and the feature sampling is only constrained inside the box, failing to effectively leverage richer context information outside. Recently, several query-based action detectors have been proposed to predict action instances in an end-to-end manner. However, they still lack adaptability in feature sampling and decoding, thus suffering from the issues of inferior performance or slower convergence. In this paper, we propose two core designs for a more flexible one-stage sparse action detector. First, we present a query-based adaptive feature sampling module, which endows the detector with the flexibility of mining a group of discriminative features from the entire spatio-temporal domain. Second, we devise a decoupled feature mixing module, which dynamically attends to and mixes video features along the spatial and temporal dimensions respectively for better feature decoding. Based on these designs, we instantiate two detection pipelines, that is, STMixer-K for keyframe action detection and STMixer-T for action tubelet detection. Without bells and whistles, our STMixer detectors obtain the state-of-the-art results on five challenging spatio-temporal action detection benchmarks for keyframe action detection or action tube detection.

Traditional video action detectors typically adopt the two-stage pipeline, where a person detector is first employed to generate actor boxes and then 3D RoIAlign is used to extract actor-specific features for classification. This detection paradigm requires multi-stage training and inference, and cannot capture context information outside the bounding box. Recently, a few query-based action detectors are proposed to predict action instances in an end-to-end manner. However, they still lack adaptability in feature sampling and decoding, thus suffering from the issues of inferior performance or slower convergence. In this paper, we propose a new one-stage sparse action detector, termed STMixer. STMixer is based on two core designs. First, we present a query-based adaptive feature sampling module, which endows our STMixer with the flexibility of mining a set of discriminative features from the entire spatiotemporal domain. Second, we devise a dual-branch feature mixing module, which allows our STMixer to dynamically attend to and mix video features along the spatial and the temporal dimension respectively for better feature decoding. Coupling these two designs with a video backbone yields an efficient end-to-end action detector. Without bells and whistles, our STMixer obtains the state-of-the-art results on the datasets of AVA, UCF101-24, and JHMDB.

Traditional object detectors employ the dense paradigm of scanning over locations and scales in an image. The recent query-based object detectors break this convention by decoding image features with a set of learnable queries. However, this paradigm still suffers from slow convergence, limited performance, and design complexity of extra networks between backbone and decoder. In this paper, we find that the key to these issues is the adaptability of decoders for casting queries to varying objects. Accordingly, we propose a fast-converging query-based detector, named AdaMixer, by improving the adaptability of query-based decoding processes in two aspects. First, each query adaptively samples features over space and scales based on estimated offsets, which allows AdaMixer to efficiently attend to the coherent regions of objects. Then, we dynamically decode these sampled features with an adaptive MLP-Mixer under the guidance of each query. Thanks to these two critical designs, AdaMixer enjoys architectural simplicity without requiring dense attentional encoders or explicit pyramid networks. On the challenging MS COCO benchmark, AdaMixer with ResNet-50 as the backbone, with 12 training epochs, reaches up to 45.0 AP on the validation set along with 27.9 APs in detecting small objects. With the longer training scheme, AdaMixer with ResNeXt-101-DCN and Swin-S reaches 49.5 and 51.3 AP. Our work sheds light on a simple, accurate, and fast converging architecture for query-based object detectors. The code is made available at https://github.com/MCG-NJU/AdaMixer.

The classification and regression head are both indispensable components to build up a dense object detector, which are usually supervised by the same training samples and thus expected to have consistency with each other for detecting objects accurately in the detection pipeline. In this paper, we break the convention of the same training samples for these two heads in dense detectors and explore a novel supervisory paradigm, termed as Mutual Supervision (MuSu), to respectively and mutually assign training samples for the classification and regression head to ensure this consistency. MuSu defines training samples for the regression head mainly based on classification predicting scores and in turn, defines samples for the classification head based on localization scores from the regression head. Experimental results show that the convergence of detectors trained by this mutual supervision is guaranteed and the effectiveness of the proposed method is verified on the challenging MS COCO benchmark. We also find that tiling more anchors at the same location benefits detectors and leads to further improvements under this training scheme. We hope this work can inspire further researches on the interaction of the classification and regression task in detection and the supervision paradigm for detectors, especially separately for these two heads.

Spatial downsampling layers are favored in convolutional neural networks (CNNs) to downscale feature maps for larger receptive fields and less memory consumption. However, for discriminative tasks, there is a possibility that these layers lose the discriminative details due to improper pooling strategies, which could hinder the learning process and eventually result in suboptimal models. In this paper, we present a unified framework over the existing downsampling layers (e.g., average pooling, max pooling, and strided convolution) from a local importance view. In this framework, we analyze the issues of these widely-used pooling layers and figure out the criteria for designing an effective downsampling layer. According to this analysis, we propose a conceptually simple, general, and effective pooling layer based on local importance modeling, termed as Local Importance-based Pooling (LIP). LIP can automatically enhance discriminative features during the downsampling procedure by learning adaptive importance weights based on inputs. Experiment results show that LIP consistently yields notable gains with different depths and different architectures on ImageNet classification. In the challenging MS COCO dataset, detectors with our LIP-ResNets as backbones obtain a consistent improvement (≥1.4%) over the vanilla ResNets, and especially achieve the current state-of-the-art performance in detecting small objects under the single-scale testing scheme1.