We present Cutie, a video object segmentation (VOS) network with object-level memory reading, which puts the object representation from memory back into the video object segmentation result. Recent works on VOS employ bottom-up pixel-level memory reading which struggles due to matching noise, especially in the presence of distractors, resulting in lower performance in more challenging data. In contrast, Cutie performs top-down object-level memory reading by adapting a small set of object queries for restructuring and interacting with the bottom-up pixel features iteratively with a query-based object transformer (qt, hence Cutie). The object queries act as a high-level summary of the target object, while high-resolution feature maps are retained for accurate segmentation. Together with foreground-background masked attention, Cutie cleanly separates the semantics of the foreground object from the background. On the challenging MOSE dataset, Cutie improves by 8.7 J&F over XMem with a similar running time and improves by 4.2 J&F over DeAOT while running three times as fast. Code is available at: https://hkchengrex.github.io/Cutie
Training data for video segmentation are expensive to annotate. This impedes extensions of end-to-end algorithms to new video segmentation tasks, especially in large-vocabulary settings. To 'track anything' without training on video data for every individual task, we develop a decoupled video segmentation approach (DEVA), composed of task-specific image-level segmentation and class/task-agnostic bi-directional temporal propagation. Due to this design, we only need an image-level model for the target task (which is cheaper to train) and a universal temporal propagation model which is trained once and generalizes across tasks. To effectively combine these two modules, we use bi-directional propagation for (semi-)online fusion of segmentation hypotheses from different frames to generate a coherent segmentation. We show that this decoupled formulation compares favorably to end-to-end approaches in several data-scarce tasks including large-vocabulary video panoptic segmentation, open-world video segmentation, referring video segmentation, and unsupervised video object segmentation. Code is available at: https://hkchengrex.github.io/Tracking-Anything-with-DEVA
The clinical explainability of convolutional neural networks (CNN) heavily relies on the joint interpretation of a model's predicted diagnostic label and associated confidence. A highly certain or uncertain model can significantly impact clinical decision-making. Thus, ensuring that confidence estimates reflect the true correctness likelihood for a prediction is essential. CNNs are often poorly calibrated and prone to overconfidence leading to improper measures of uncertainty. This creates the need for confidence calibration. However, accuracy and performance-based evaluations of CNNs are commonly used as the sole benchmark for medical tasks. Taking into consideration the risks associated with miscalibration is of high importance. In recent years, modern augmentation techniques, which cut, mix, and combine images, have been introduced. Such augmentations have benefited CNNs through regularization, robustness to adversarial samples, and calibration. Standard augmentations based on image scaling, rotating, and zooming, are widely leveraged in the medical domain to combat the scarcity of data. In this paper, we evaluate the effects of three modern augmentation techniques, CutMix, MixUp, and CutOut on the calibration and performance of CNNs for medical tasks. CutMix improved calibration the most while CutOut often lowered the level of calibration.
Learning computer vision models from (and for) movies has a long-standing history. While great progress has been attained, there is still a need for a pretrained multimodal model that can perform well in the ever-growing set of movie understanding tasks the community has been establishing. In this work, we introduce Long-range Multimodal Pretraining, a strategy, and a model that leverages movie data to train transferable multimodal and cross-modal encoders. Our key idea is to learn from all modalities in a movie by observing and extracting relationships over a long-range. After pretraining, we run ablation studies on the LVU benchmark and validate our modeling choices and the importance of learning from long-range time spans. Our model achieves state-of-the-art on several LVU tasks while being much more data efficient than previous works. Finally, we evaluate our model's transferability by setting a new state-of-the-art in five different benchmarks.
Despite advancements in user-guided video segmentation, extracting complex objects consistently for highly complex scenes is still a labor-intensive task, especially for production. It is not uncommon that a majority of frames need to be annotated. We introduce a novel semi-supervised video object segmentation (SSVOS) model, XMem++, that improves existing memory-based models, with a permanent memory module. Most existing methods focus on single frame annotations, while our approach can effectively handle multiple user-selected frames with varying appearances of the same object or region. Our method can extract highly consistent results while keeping the required number of frame annotations low. We further introduce an iterative and attention-based frame suggestion mechanism, which computes the next best frame for annotation. Our method is real-time and does not require retraining after each user input. We also introduce a new dataset, PUMaVOS, which covers new challenging use cases not found in previous benchmarks. We demonstrate SOTA performance on challenging (partial and multi-class) segmentation scenarios as well as long videos, while ensuring significantly fewer frame annotations than any existing method. Project page: https://max810.github.io/xmem2-project-page/
We present Interactive Neural Video Editing (INVE), a real-time video editing solution, which can assist the video editing process by consistently propagating sparse frame edits to the entire video clip. Our method is inspired by the recent work on Layered Neural Atlas (LNA). LNA, however, suffers from two major drawbacks: (1) the method is too slow for interactive editing, and (2) it offers insufficient support for some editing use cases, including direct frame editing and rigid texture tracking. To address these challenges we leverage and adopt highly efficient network architectures, powered by hash-grids encoding, to substantially improve processing speed. In addition, we learn bi-directional functions between image-atlas and introduce vectorized editing, which collectively enables a much greater variety of edits in both the atlas and the frames directly. Compared to LNA, our INVE reduces the learning and inference time by a factor of 5, and supports various video editing operations that LNA cannot. We showcase the superiority of INVE over LNA in interactive video editing through a comprehensive quantitative and qualitative analysis, highlighting its numerous advantages and improved performance. For video results, please see https://gabriel-huang.github.io/inve/
The tracking-by-detection paradigm today has become the dominant method for multi-object tracking and works by detecting objects in each frame and then performing data association across frames. However, its sequential frame-wise matching property fundamentally suffers from the intermediate interruptions in a video, such as object occlusions, fast camera movements, and abrupt light changes. Moreover, it typically overlooks temporal information beyond the two frames for matching. In this paper, we investigate an alternative by treating object association as clip-wise matching. Our new perspective views a single long video sequence as multiple short clips, and then the tracking is performed both within and between the clips. The benefits of this new approach are two folds. First, our method is robust to tracking error accumulation or propagation, as the video chunking allows bypassing the interrupted frames, and the short clip tracking avoids the conventional error-prone long-term track memory management. Second, the multiple frame information is aggregated during the clip-wise matching, resulting in a more accurate long-range track association than the current frame-wise matching. Given the state-of-the-art tracking-by-detection tracker, QDTrack, we showcase how the tracking performance improves with our new tracking formulation. We evaluate our proposals on two tracking benchmarks, TAO and MOT17 that have complementary characteristics and challenges each other.
Scaling object taxonomies is one of the important steps toward a robust real-world deployment of recognition systems. We have faced remarkable progress in images since the introduction of the LVIS benchmark. To continue this success in videos, a new video benchmark, TAO, was recently presented. Given the recent encouraging results from both detection and tracking communities, we are interested in marrying those two advances and building a strong large vocabulary video tracker. However, supervisions in LVIS and TAO are inherently sparse or even missing, posing two new challenges for training the large vocabulary trackers. First, no tracking supervisions are in LVIS, which leads to inconsistent learning of detection (with LVIS and TAO) and tracking (only with TAO). Second, the detection supervisions in TAO are partial, which results in catastrophic forgetting of absent LVIS categories during video fine-tuning. To resolve these challenges, we present a simple but effective learning framework that takes full advantage of all available training data to learn detection and tracking while not losing any LVIS categories to recognize. With this new learning scheme, we show that consistent improvements of various large vocabulary trackers are capable, setting strong baseline results on the challenging TAO benchmarks.
This paper investigates the challenge of extracting highlight moments from videos. To perform this task, a system needs to understand what constitutes a highlight for arbitrary video domains while at the same time being able to scale across different domains. Our key insight is that photographs taken by photographers tend to capture the most remarkable or photogenic moments of an activity. Drawing on this insight, we present Videogenic, a system capable of creating domain-specific highlight videos for a wide range of domains. In a human evaluation study (N=50), we show that a high-quality photograph collection combined with CLIP-based retrieval (which uses a neural network with semantic knowledge of images) can serve as an excellent prior for finding video highlights. In a within-subjects expert study (N=12), we demonstrate the usefulness of Videogenic in helping video editors create highlight videos with lighter workload, shorter task completion time, and better usability.