REVIEW 6 cited by
DELTA: degradation-free fully test-time adaptation
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Fully test-time adaptation aims at adapting a pre-trained model to the test stream during real-time inference, which is urgently required when the test distribution differs from the training distribution. Several efforts have been devoted to improving adaptation performance. However, we find that two unfavorable defects are concealed in the prevalent adaptation methodologies like test-time batch normalization (BN) and self-learning. First, we reveal that the normalization statistics in test-time BN are completely affected by the currently received test samples, resulting in inaccurate estimates. Second, we show that during test-time adaptation, the parameter update is biased towards some dominant classes. In addition to the extensively studied test stream with independent and class-balanced samples, we further observe that the defects can be exacerbated in more complicated test environments, such as (time) dependent or class-imbalanced data. We observe that previous approaches work well in certain scenarios while show performance degradation in others due to their faults. In this paper, we provide a plug-in solution called DELTA for Degradation-freE fuLly Test-time Adaptation, which consists of two components: (i) Test-time Batch Renormalization (TBR), introduced to improve the estimated normalization statistics. (ii) Dynamic Online re-weighTing (DOT), designed to address the class bias within optimization. We investigate various test-time adaptation methods on three commonly used datasets with four scenarios, and a newly introduced real-world dataset. DELTA can help them deal with all scenarios simultaneously, leading to SOTA performance.
Forward citations
Cited by 6 Pith papers
-
Test-Time Curriculum for Open-Set AIGC Detection
A curriculum-based test-time adaptation method, using balanced confident pseudo-labels and multi-scale refinement, improves AIGC detector accuracy on unseen generators by 11 to 29 points over its starting detector.
-
Memory-Supported Synergistic Adaptation for Training-Free Test-Time Medical Image Segmentation
MSSA improves test-time medical image segmentation by storing reliable vision-language predictions in a memory bank and using stored images as prototypes to segment new images, without updating model weights.
-
Dual Distribution Estimation for Zero-shot Noisy Test-Time Adaptation with VLMs
DDE models class-wise positive feature Gaussians and negative label distributions to boost ID accuracy and OOD detection in zero-shot noisy TTA, reporting 3.70% harmonic mean gain and 6.20% FPR95 drop on ImageNet.
-
Hierarchical Consistency Learning for Test-time Adaptation in Camouflage Perception
Proposes HCL framework with HRR, TAG, and PCC modules for test-time adaptation in camouflaged object detection, claiming consistent outperformance on benchmarks under distribution shifts.
-
Enhancing Novel View Synthesis from extremely sparse views with SfM-free 3D Gaussian Splatting Framework
SfM-free 3D Gaussian Splatting jointly estimates camera poses and geometry from two views and reports a 2.75 dB PSNR improvement over existing 3DGS methods on extremely sparse inputs.
-
DoSReMC: Domain Shift Resilient Mammography Classification using Batch Normalization Adaptation
DoSReMC improves cross-domain generalization in mammography classification by fine-tuning only batch normalization and fully connected layers of pretrained CNNs while preserving convolutional filters, combined with ad...
Discussion (0). Sign in to comment.