-
1
-
2
-
3
Lifelong benchmarks: efficient model evaluation in an era of rapid progress
Published 2024“…Standardized benchmarks drive progress in machine learning. However, with repeated testing, the risk of overfitting grows as algorithms overexploit benchmark idiosyncrasies. …”
Conference item -
4
Adversarial metric attack and defense for person re-identification
Published 2020“…Meanwhile, we also present an early attempt of training a metric-preserving network, thereby defending the metric against adversarial attacks. At last, by benchmarking various adversarial settings, we expect that our work can facilitate the development of adversarial attack and defense in metric-based applications. …”
Journal article -
5
The seventh visual object tracking VOT2019 Challenge results
Published 2020“…The Visual Object Tracking challenge VOT2019 is the seventh annual tracker benchmarking activity organized by the VOT initiative. …”
Conference item -
6
No "zero-shot" without exponential data: pretraining concept frequency determines multimodal model performance
Published 2024“…Furthermore, upon benchmarking models on long-tailed data sampled based on our analysis, we demonstrate that multimodal models across the board perform poorly. …”
Conference item -
7
Raising the bar on the evaluation of out-of-distribution detection
Published 2023“…Through extensive experiments on MNIST, CIFAR-10/100 and ImageNet, we show that a) state-of-the-art OoD detection methods which perform exceedingly well on conventional benchmarks are significantly less robust to our proposed benchmark. …”
Conference item -
8
Gradient matching for domain generalization
Published 2022“…We perform experiments on the WILDS benchmark, which captures distribution shift in the real world, as well as the DOMAINBED benchmark that focuses more on synthetic-to-real transfer. …”
Conference item -
9
SiamMask: A framework for fast online object tracking and segmentation
Published 2023“…It yields real-time state-of-the art results on visual-object tracking benchmarks, while at the same time demonstrating competitive performance at a high speed for video object segmentation benchmarks.…”
Journal article -
10
Holistically-attracted wireframe parsing
Published 2020“…On both benchmarks, it obtains state-of-the-art performance in terms of accuracy and efficiency. …”
Conference item -
11
Automated and verified deep learning
Published 2021“…Third, we show an application by tackling video segmentation as a meta learning problem and demonstrating state-of-the-art results on common benchmarks.</p>…”
Thesis -
12
Devon: deformable volume network for learning optical flow
Published 2020“…Experiments show Devon is more suitable in handling small objects moving fast and achieves comparable results to the state-of-the-art methods in public benchmarks.…”
Conference item -
13
Separable flow: learning motion cost volumes for optical flow estimation
Published 2022“…Our method leads both the now standard Sintel and KITTI optical flow benchmarks in terms of accuracy, and is also shown to generalize better from synthetic to real data.…”
Conference item -
14
The Thermal Infrared Visual Object Tracking VOT-TIR2015 challenge results
Published 2016“…VOT-TIR2015 is the first benchmark on short-term tracking in TIR sequences. …”
Conference item -
15
The visual object tracking VOT2015 challenge results
Published 2016“…The number of tested trackers makes VOT 2015 the largest benchmark on short-term tracking to date. For each participating tracker, a short description is provided in the appendix. …”
Conference item -
16
Fully-convolutional Siamese networks for object tracking
Published 2016“…Our tracker operates at frame-rates beyond real-time and, despite its extreme simplicity, achieves state-of-the-art performance in multiple benchmarks.…”
Conference item -
17
Siam R-CNN: visual tracking by re-detection
Published 2020“…Siam R-CNN achieves the current best performance on ten tracking benchmarks, with especially strong results for long-term tracking. …”
Conference item -
18
The visual object tracking VOT2016 challenge results
Published 2016“…The number of tested state-of-the-art trackers makes the VOT 2016 the largest and most challenging benchmark on short-term tracking to date. For each participating tracker, a short description is provided in the Appendix. …”
Conference item -
19
Continual learning in low-rank orthogonal subspaces
Published 2020“…To the best of our understanding, we report, for the first time, strong results over experience-replay baseline with and without memory on standard classification benchmarks in continual learning.…”
Conference item -
20
Open vocabulary semantic segmentation with Patch Aligned Contrastive Learning
Published 2023“…Using pre-trained CLIP encoders with PACL, we are able to set the state-of-the-art on the task of open vocabulary zero-shot segmentation on 4 different segmentation benchmarks: Pascal VOC, Pascal Context, COCO Stuff and ADE20K. …”
Conference item