9 papers
Training Crossroads for Recurrent Vision Transformers: Recurrence, Neural ODEs, and Deep Supervision
Grzegorz Gruszczynski, Pawel Olszowiec, Michal Byra +2
Vision Transformers (ViTs) achieve strong image-recognition performance, but their parameter count grows linearly with depth when each block is independently parameterized. Single-…
t-gems: text-guided exit modules for decreasing clip image encoder
Alberto Presta, Grzegorz Stefanski, Michal Byra +1
Multimodal deep neural networks enhance deep comprehension by integrating diverse data modalities. Data from different modalities are typically projected into a shared latent space…
bViT: Investigating Single-Block Recurrence in Vision Transformers for Image Recognition
Michal Byra, Pawel Olszowiec, Grzegorz Stefanski +2
Vision Transformers (ViTs) are built by stacking independently parameterized blocks, but it remains unclear how much of this depth requires layer specific transformations and how m…
Routing the Lottery: Adaptive Subnetworks for Heterogeneous Data
Grzegorz Stefanski, Alberto Presta, Michal Byra
In pruning, the Lottery Ticket Hypothesis posits that large networks contain sparse subnetworks, or winning tickets, that can be trained in isolation to match the performance of th…
Denoising Diffusion Probabilistic Model for Point Cloud Compression at Low Bit-Rates
Gabriele Spadaro, Alberto Presta, Jhony H. Giraldo +5
Efficient compression of low-bit-rate point clouds is critical for bandwidth-constrained applications. However, existing techniques mainly focus on high-fidelity reconstruction, re…
Efficient Progressive Image Compression with Variance-aware Masking
Alberto Presta, Enzo Tartaglione, Attilio Fiandrotti +2
Learned progressive image compression is gaining momentum as it allows improved image reconstruction as more bits are decoded at the receiver. We propose a progressive image compre…