Spatial-Temporal Multi-level Association for Video Object Segmentation

Existing semi-supervised video object segmentation methods either focus on temporal feature matching or spatial-temporal feature modeling. However, they do not address the issues of sufficient target interaction and efficient parallel processing simultaneously, thereby constraining the learning of dynamic, target-aware features. To tackle these limitations, this paper proposes a spatial-temporal multi-level association framework, which jointly associates reference frame, test frame, and object features to achieve sufficient interaction and parallel target ID association with a spatial-temporal memory bank for efficient video object segmentation. Specifically, we construct a spatial-temporal multi-level feature association module to learn better target-aware features, which formulates feature extraction and interaction as the efficient operations of object self-attention, reference object enhancement, and test reference correlation. In addition, we propose a spatial-temporal memory to assist feature association and temporal ID assignment and correlation. We evaluate the proposed method by conducting extensive experiments on numerous video object segmentation datasets, including DAVIS 2016/2017 val, DAVIS 2017 test-dev, and YouTube-VOS 2018/2019 val. The favorable performance against the state-of-the-art methods demonstrates the effectiveness of our approach. All source code and trained models will be made publicly available.

Mansformer: Efficient Transformer of Mixed Attention for Image Deblurring and Beyond

Transformer has made an enormous success in natural language processing and high-level vision over the past few years. However, the complexity of self-attention is quadratic to the image size, which makes it infeasible for high-resolution vision tasks. In this paper, we propose the Mansformer, a Transformer of mixed attention that combines multiple self-attentions, gate, and multi-layer perceptions (MLPs), to explore and employ more possibilities of self-attention. Taking efficiency into account, we design four kinds of self-attention, whose complexities are all linear. By elaborate adjustment of the tensor shapes and dimensions for the dot product, we split the typical self-attention of quadratic complexity into four operations of linear complexity. To adaptively merge these different kinds of self-attention, we take advantage of an architecture similar to Squeeze-and-Excitation Networks. Furthermore, we make it to merge the two-staged Transformer design into one stage by the proposed gated-dconv MLP. Image deblurring is our main target, while extensive quantitative and qualitative evaluations show that this method performs favorably against the state-of-the-art methods far more than simply deblurring. The source codes and trained models will be made available to the public.

HENet: Hybrid Encoding for End-to-end Multi-task 3D Perception from Multi-view Cameras

Three-dimensional perception from multi-view cameras is a crucial component in autonomous driving systems, which involves multiple tasks like 3D object detection and bird's-eye-view (BEV) semantic segmentation. To improve perception precision, large image encoders, high-resolution images, and long-term temporal inputs have been adopted in recent 3D perception models, bringing remarkable performance gains. However, these techniques are often incompatible in training and inference scenarios due to computational resource constraints. Besides, modern autonomous driving systems prefer to adopt an end-to-end framework for multi-task 3D perception, which can simplify the overall system architecture and reduce the implementation complexity. However, conflict between tasks often arises when optimizing multiple tasks jointly within an end-to-end 3D perception model. To alleviate these issues, we present an end-to-end framework named HENet for multi-task 3D perception in this paper. Specifically, we propose a hybrid image encoding network, using a large image encoder for short-term frames and a small image encoder for long-term temporal frames. Then, we introduce a temporal feature integration module based on the attention mechanism to fuse the features of different frames extracted by the two aforementioned hybrid image encoders. Finally, according to the characteristics of each perception task, we utilize BEV features of different grid sizes, independent BEV encoders, and task decoders for different tasks. Experimental results show that HENet achieves state-of-the-art end-to-end multi-task 3D perception results on the nuScenes benchmark, including 3D object detection and BEV semantic segmentation. The source code and models will be released at https://github.com/VDIGPKU/HENet.

Dynamic Pre-training: Towards Efficient and Scalable All-in-One Image Restoration

All-in-one image restoration tackles different types of degradations with a unified model instead of having task-specific, non-generic models for each degradation. The requirement to tackle multiple degradations using the same model can lead to high-complexity designs with fixed configuration that lack the adaptability to more efficient alternatives. We propose DyNet, a dynamic family of networks designed in an encoder-decoder style for all-in-one image restoration tasks. Our DyNet can seamlessly switch between its bulkier and lightweight variants, thereby offering flexibility for efficient model deployment with a single round of training. This seamless switching is enabled by our weights-sharing mechanism, forming the core of our architecture and facilitating the reuse of initialized module weights. Further, to establish robust weights initialization, we introduce a dynamic pre-training strategy that trains variants of the proposed DyNet concurrently, thereby achieving a 50% reduction in GPU hours. To tackle the unavailability of large-scale dataset required in pre-training, we curate a high-quality, high-resolution image dataset named Million-IRD having 2M image samples. We validate our DyNet for image denoising, deraining, and dehazing in all-in-one setting, achieving state-of-the-art results with 31.34% reduction in GFlops and a 56.75% reduction in parameters compared to baseline models. The source codes and trained models are available at https://github.com/akshaydudhane16/DyNet.

RTracker: Recoverable Tracking via PN Tree Structured Memory

Existing tracking methods mainly focus on learning better target representation or developing more robust prediction models to improve tracking performance. While tracking performance has significantly improved, the target loss issue occurs frequently due to tracking failures, complete occlusion, or out-of-view situations. However, considerably less attention is paid to the self-recovery issue of tracking methods, which is crucial for practical applications. To this end, we propose a recoverable tracking framework, RTracker, that uses a tree-structured memory to dynamically associate a tracker and a detector to enable self-recovery ability. Specifically, we propose a Positive-Negative Tree-structured memory to chronologically store and maintain positive and negative target samples. Upon the PN tree memory, we develop corresponding walking rules for determining the state of the target and define a set of control flows to unite the tracker and the detector in different tracking scenarios. Our core idea is to use the support samples of positive and negative target categories to establish a relative distance-based criterion for a reliable assessment of target loss. The favorable performance in comparison against the state-of-the-art methods on numerous challenging benchmarks demonstrates the effectiveness of the proposed algorithm.

Efficient Video Object Segmentation via Modulated Cross-Attention Memory

Recently, transformer-based approaches have shown promising results for semi-supervised video object segmentation. However, these approaches typically struggle on long videos due to increased GPU memory demands, as they frequently expand the memory bank every few frames. We propose a transformer-based approach, named MAVOS, that introduces an optimized and dynamic long-term modulated cross-attention (MCA) memory to model temporal smoothness without requiring frequent memory expansion. The proposed MCA effectively encodes both local and global features at various levels of granularity while efficiently maintaining consistent speed regardless of the video length. Extensive experiments on multiple benchmarks, LVOS, Long-Time Video, and DAVIS 2017, demonstrate the effectiveness of our proposed contributions leading to real-time inference and markedly reduced memory demands without any degradation in segmentation accuracy on long videos. Compared to the best existing transformer-based approach, our MAVOS increases the speed by 7.6x, while significantly reducing the GPU memory by 87% with comparable segmentation performance on short and long video datasets. Notably on the LVOS dataset, our MAVOS achieves a J&F score of 63.3% while operating at 37 frames per second (FPS) on a single V100 GPU. Our code and models will be publicly available at: https://github.com/Amshaker/MAVOS.

Panda-70M: Captioning 70M Videos with Multiple Cross-Modality Teachers

The quality of the data and annotation upper-bounds the quality of a downstream model. While there exist large text corpora and image-text pairs, high-quality video-text data is much harder to collect. First of all, manual labeling is more time-consuming, as it requires an annotator to watch an entire video. Second, videos have a temporal dimension, consisting of several scenes stacked together, and showing multiple actions. Accordingly, to establish a video dataset with high-quality captions, we propose an automatic approach leveraging multimodal inputs, such as textual video description, subtitles, and individual video frames. Specifically, we curate 3.8M high-resolution videos from the publicly available HD-VILA-100M dataset. We then split them into semantically consistent video clips, and apply multiple cross-modality teacher models to obtain captions for each video. Next, we finetune a retrieval model on a small subset where the best caption of each video is manually selected and then employ the model in the whole dataset to select the best caption as the annotation. In this way, we get 70M videos paired with high-quality text captions. We dub the dataset as Panda-70M. We show the value of the proposed dataset on three downstream tasks: video captioning, video and text retrieval, and text-driven video generation. The models trained on the proposed data score substantially better on the majority of metrics across all the tasks.

Interactive Multi-Head Self-Attention with Linear Complexity

We propose an efficient interactive method for multi-head self-attention via decomposition. For existing methods using multi-head self-attention, the attention operation of each head is computed independently. However, we show that the interactions between cross-heads of the attention matrix enhance the information flow of the attention operation. Considering that the attention matrix of each head can be seen as a feature of networks, it is beneficial to establish connectivity between them to capture interactions better. However, a straightforward approach to capture the interactions between the cross-heads is computationally prohibitive as the complexity grows substantially with the high dimension of an attention matrix. In this work, we propose an effective method to decompose the attention operation into query- and key-less components. This will result in a more manageable size for the attention matrix, specifically for the cross-head interactions. Expensive experimental results show that the proposed cross-head interaction approach performs favorably against existing efficient attention methods and state-of-the-art backbone models.

Scene Prior Filtering for Depth Map Super-Resolution

Multi-modal fusion is vital to the success of super-resolution of depth maps. However, commonly used fusion strategies, such as addition and concatenation, fall short of effectively bridging the modal gap. As a result, guided image filtering methods have been introduced to mitigate this issue. Nevertheless, it is observed that their filter kernels usually encounter significant texture interference and edge inaccuracy. To tackle these two challenges, we introduce a Scene Prior Filtering network, SPFNet, which utilizes the priors surface normal and semantic map from large-scale models. Specifically, we design an All-in-one Prior Propagation that computes the similarity between multi-modal scene priors, i.e., RGB, normal, semantic, and depth, to reduce the texture interference. In addition, we present a One-to-one Prior Embedding that continuously embeds each single-modal prior into depth using Mutual Guided Filtering, further alleviating the texture interference while enhancing edges. Our SPFNet has been extensively evaluated on both real and synthetic datasets, achieving state-of-the-art performance.

StyleDubber: Towards Multi-Scale Style Learning for Movie Dubbing

Given a script, the challenge in Movie Dubbing (Visual Voice Cloning, V2C) is to generate speech that aligns well with the video in both time and emotion, based on the tone of a reference audio track. Existing state-of-the-art V2C models break the phonemes in the script according to the divisions between video frames, which solves the temporal alignment problem but leads to incomplete phoneme pronunciation and poor identity stability. To address this problem, we propose StyleDubber, which switches dubbing learning from the frame level to phoneme level. It contains three main components: (1) A multimodal style adaptor operating at the phoneme level to learn pronunciation style from the reference audio, and generate intermediate representations informed by the facial emotion presented in the video; (2) An utterance-level style learning module, which guides both the mel-spectrogram decoding and the refining processes from the intermediate embeddings to improve the overall style expression; And (3) a phoneme-guided lip aligner to maintain lip sync. Extensive experiments on two of the primary benchmarks, V2C and Grid, demonstrate the favorable performance of the proposed method as compared to the current state-of-the-art. The source code and trained models will be released to the public.