import torch
import torch.nn as nn
[docs]class SupConLoss(nn.Module):
"""Supervised Contrastive Learning.
It also supports the unsupervised contrastive loss in
SimCLR: A Simple Framework for Contrastive Learning of Visual Representations
References:
[1] https://github.com/HobbitLong/SupContrast
[2] https://arxiv.org/pdf/2004.11362.pdf
[3] https://arxiv.org/abs/2002.05709
"""
def __init__(self, temperature=0.07, contrast_mode="all", base_temperature=0.07):
super(SupConLoss, self).__init__()
self.temperature = temperature
self.contrast_mode = contrast_mode
self.base_temperature = base_temperature
[docs] def forward(self, features, labels=None, mask=None):
"""Compute loss for model. If both `labels` and `mask` are None,
it degenerates to SimCLR unsupervised loss.
Args:
features: hidden vector of shape [bsz, n_views, ...].
labels: ground truth of shape [bsz].
mask: contrastive mask of shape [bsz, bsz], mask_{i,j}=1 if sample j
has the same class as sample i. Can be asymmetric.
Returns:
A loss scalar.
"""
device = torch.device("cuda") if features.is_cuda else torch.device("cpu")
if len(features.shape) < 3:
raise ValueError("`features` needs to be [bsz, n_views, ...]," "at least 3 dimensions are required")
if len(features.shape) > 3:
features = features.view(features.shape[0], features.shape[1], -1)
batch_size = features.shape[0]
if labels is not None and mask is not None:
raise ValueError("Cannot define both `labels` and `mask`")
elif labels is None and mask is None:
mask = torch.eye(batch_size, dtype=torch.float32).to(device)
elif labels is not None:
labels = labels.contiguous().view(-1, 1)
if labels.shape[0] != batch_size:
raise ValueError("Num of labels does not match num of features")
mask = torch.eq(labels, labels.T).float().to(device)
else:
mask = mask.float().to(device)
contrast_count = features.shape[1]
contrast_feature = torch.cat(torch.unbind(features, dim=1), dim=0)
if self.contrast_mode == "one":
anchor_feature = features[:, 0]
anchor_count = 1
elif self.contrast_mode == "all":
anchor_feature = contrast_feature
anchor_count = contrast_count
else:
raise ValueError("Unknown mode: {}".format(self.contrast_mode))
# compute logits
anchor_dot_contrast = torch.div(torch.matmul(anchor_feature, contrast_feature.T), self.temperature)
# for numerical stability
logits_max, _ = torch.max(anchor_dot_contrast, dim=1, keepdim=True)
logits = anchor_dot_contrast - logits_max.detach()
# tile mask
mask = mask.repeat(anchor_count, contrast_count)
# mask-out self-contrast cases
logits_mask = torch.scatter(
torch.ones_like(mask), 1, torch.arange(batch_size * anchor_count).view(-1, 1).to(device), 0
)
mask = mask * logits_mask
# compute log_prob
exp_logits = torch.exp(logits) * logits_mask
log_prob = logits - torch.log(exp_logits.sum(1, keepdim=True))
# compute mean of log-likelihood over positive
mean_log_prob_pos = (mask * log_prob).sum(1) / mask.sum(1)
# loss
loss = -(self.temperature / self.base_temperature) * mean_log_prob_pos
loss = loss.view(anchor_count, batch_size).mean()
return loss
[docs]class CSILoss(SupConLoss):
"""Contrasting shifted instances (con-SI) loss.
References:
[1] https://arxiv.org/abs/2007.08176
"""
def __init__(self, temperature=0.07, contrast_mode="all", base_temperature=0.07, lbd=1):
super().__init__(temperature=temperature, contrast_mode=contrast_mode, base_temperature=base_temperature)
self.lbd = lbd
self.shift_criterion = nn.CrossEntropyLoss()
[docs] def forward(self, features, shift_labels, labels=None, mask=None):
loss_sim = super().forward(features, labels, mask)
loss_shift = self.shift_criterion(features, shift_labels)
return loss_sim + self.lbd * loss_shift